{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-and-robust-dynamic-hand-gesture","title":"Fast and Robust Dynamic Hand Gesture Recognition via Key Frames Extraction and Feature Fusion","arxiv_id":"1901.04622","date":"2019-01-15","proceeding":null,"authors":["Hao Tang","Hong Liu","Wei Xiao","Nicu Sebe"],"abstract":"Gesture recognition is a hot topic in computer vision and pattern\nrecognition, which plays a vitally important role in natural human-computer\ninterface. Although great progress has been made recently, fast and robust hand\ngesture recognition remains an open problem, since the existing methods have\nnot well balanced the performance and the efficiency simultaneously. To bridge\nit, this work combines image entropy and density clustering to exploit the key\nframes from hand gesture video for further feature extraction, which can\nimprove the efficiency of recognition. Moreover, a feature fusion strategy is\nalso proposed to further improve feature representation, which elevates the\nperformance of recognition. To validate our approach in a \"wild\" environment,\nwe also introduce two new datasets called HandGesture and Action3D datasets.\nExperiments consistently demonstrate that our strategy achieves competitive\nresults on Northwestern University, Cambridge, HandGesture and Action3D hand\ngesture datasets. Our code and datasets will release at\nhttps://github.com/Ha0Tang/HandGestureRecognition.","url_abs":"http://arxiv.org/abs/1901.04622v1","url_pdf":"http://arxiv.org/pdf/1901.04622v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-and-robust-dynamic-hand-gesture","repo_url":"https://github.com/Ha0Tang/HandGestureRecognition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"},{"task_slug":"hand-gesture-recognition","task_name":"Hand Gesture Recognition"},{"task_slug":"hand-gesture-recognition-1","task_name":"Hand-Gesture Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hand-gesture-recognition-on-cambridge","task":"Hand Gesture Recognition","dataset":"Cambridge","model":"Key Frames + Feature Fusion","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"98.23%"},"uses_additional_data":false},{"leaderboard":"/sota/hand-gesture-recognition-on-northwestern","task":"Hand Gesture Recognition","dataset":"Northwestern University","model":"Key Frames + Feature Fusion","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"96.89"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.04622","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}